A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Text-independent speaker identification based on explicit exploitation of stochastic characteristics of test utterance
2001
Electronics Letters
Preserved Fulltext
higher resolution of time-frequency by wavelets and its capabilities for non-stationary analysis is useful for detecting the sudden burst in the signal that is useful for classification. In addition these features are found to be more robust than the features of MFCC and the 24-band filter based on AWP. 0 IEE 2001
doi:10.1049/el:20011044
fatcat:udltfglroffsfgpfisn7vfguxu